Ontological supervision for fine grained classification of Street View storefronts

By Yair Movshovitz-Attias, Qian Yu, Martin C. Stumpe, Vinay D. Shet, Sacha Arnoud, Liron Yatziv. 2015

84 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Geography, Planning and Development

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Rethinking the Inception Architecture for Computer Vision (2015, methodology): “This has made it feasible to utilize Inception networks in big-data scenarios[17], [13], where huge amount of data needed to be processed at reasonable cost or scenarios where memory or computational capacity is inherently limited, for example in mobile vision settings.”
Learning to Learn: Model Regression Networks for Easy Small Sample Learning (2016, background): “, unlabeled examples that do not belong to the concerned classes) for max-margin regularization [98], and 5) synthesize new virtual examples, either rendered explicitly with computer graphics techniques or created implicitly through compositional representations [67, 66, 71, 106, 21, 18].”
Combining multiple sources of knowledge in deep CNNs for action recognition (2016, background): “Recent work has shown that CNNs can even recognize and take advantage of characters on signs of store for store front classification in large scale street view datasets without any supervision about where the text is located or what type of characters are depicted[16].”
Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images (2017, methodology): “This is the reason of using Inception networks in big data analysis where huge amount of data needed to be processed at reasonable time and computational cost (Movshovitz-Attias et al., 2015; Schroff et al., 2015).”
How Useful Is Photo-Realistic Rendering for Visual Learning? (2016, background): “This decrease ushered in a new era in computer vision, one that makes use of highly distributed inference methods [7, 8] and massive amounts of labeled data [9, 10, 11].”
Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization (2019, methodology): “We employed a deep neural network (DNN) for embryo image analysis based on Google’s Inception-V1(21) architecture, which offers an effective run-time and computational cost.(44,45) Convolutional neural networks (CNNs) comprise several convolutions to pass the result to the next layer, pooling layers”